arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1702.07360stat.MLcs.LG
收藏

神经决策树

Neural Decision Trees

Rice University(莱斯大学)

Randall Balestriero

摘要:

在本文中,我们提出了一个协同融合的神经网络和决策树(DT),我们称之为神经决策树(NDT)。NDT是一种决策树结构,其中每个分裂节点是一个独立的多层感知器,如果使用多个层,则允许斜决策函数或任意非线性决策函数。这样,每个MLP可以被看作树的一个节点。然后,我们表明,与这些单位之间的权重共享asumption,我们最终与散列神经网络(HNN),这是一个多层感知器与sigmoid激活函数的最后一层,而不是标准的softmax。然后,输出单元共同表示在特定区域中的概率。建议的框架允许全局优化,而不是贪婪的DT和微分w.r.t.所有参数和输入,允许轻松集成到任何可学习的管道中,例如在用于计算机视觉任务的CNN之后。我们还展示了HNN的建模能力,允许学习不相交区域的联合以进行最终聚类或分类,使其比需要线性可分性的标准softmax MLP更通用和强大,从而减少了对内层执行复杂数据转换的需求。最后,我们展示了监督,半监督和无监督任务的实验,并将结果与标准DT和MLP进行比较。

英文摘要:

In this paper we propose a synergistic melting of neural networks and decision trees (DT) we call neural decision trees (NDT). NDT is an architecture a la decision tree where each splitting node is an independent multilayer perceptron allowing oblique decision functions or arbritrary nonlinear decision function if more than one layer is used. This way, each MLP can be seen as a node of the tree. We then show that with the weight sharing asumption among those units, we end up with a Hashing Neural Network (HNN) which is a multilayer perceptron with sigmoid activation function for the last layer as opposed to the standard softmax. The output units then jointly represent the probability to be in a particular region. The proposed framework allows for global optimization as opposed to greedy in DT and differentiability w.r.t. all parameters and the input, allowing easy integration in any learnable pipeline, for example after CNNs for computer vision tasks. We also demonstrate the modeling power of HNN allowing to learn union of disjoint regions for final clustering or classification making it more general and powerful than standard softmax MLP requiring linear separability thus reducing the need on the inner layer to perform complex data transformations. We finally show experiments for supervised, semi-suppervised and unsupervised tasks and compare results with standard DTs and MLPs.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑